© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 2755
    Prev
    Next
    INDEX
    Explanations

    phrases indicating customer dissatisfaction or negative experiences with services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بتوان
    -0.96
     itself
    -0.60
     می‌توان
    -0.60
     Itself
    -0.59
     kendisi
    -0.57
     dirinya
    -0.54
    itself
    -0.50
     pihaknya
    -0.48
     خودش
    -0.47
     préfère
    -0.46
    POSITIVE LOGITS
     yourself
    2.28
     yourselves
    1.77
    yourself
    1.66
     your
    1.55
     Yourself
    1.45
     YOURSELF
    1.34
    Yourself
    1.21
    your
    1.16
    你自己
    1.02
     будете
    0.99
    Activations Density 1.223%

    No Known Activations